Blog

Product Delivery Reinforcement Learning


Product Delivery Reinforcement Learning

Accenture partnered with San Francisco based AI company Pathmind to investigate the potential of new reinforcement learning (RL) opportunities in simulation.

The results obtained were extremely good. The method produced a waiting time more than 4x shorter than the Nearest Agent heuristic.

In this blog, Agustin Albinati summarizes the model, introduces the three key considerations when defining the neural net, and presents the results of his team's investigations. Linked at the end of the blog is a step by step how-to with Pathmind. Read on!

Q&A: COVID-19 Mass Vaccination — Simulation, AI Application and Real-World Implementation


Q&A: COVID-19 Mass Vaccination — Simulation, AI Application and Real-World Implementation

As COVID-19 vaccines have become available, many challenges have needed resolving. Not least, ensuring sufficient supply and effective distribution.

At our webinar, March 2021, guest presenter Dr. Ali Asgary of York University, Canada, gave insight into the development and use of a drive-through mass COVID-19 vaccination simulation. He provided details of its machine learning model and online application, including how public authorities are using the results in their vaccination rollouts. Here are the webinar details, recording, and Q&A answers.

How to use AnyLogic Cloud: 5 typical scenarios


How to use AnyLogic Cloud: 5 typical scenarios

In 2017, we released AnyLogic Cloud to the public. With a userbase of around 10,000 modelers, it is now the largest public online platform for people working in simulation.

The public version of the service is available to everyone, allowing them to run models and experiments. Online models and experiment results can be shared online and run from a browser. The platform leverages the advantages of cloud computing: this way complex experiments are performed faster than on a regular computer, and the quality of animation depends minimally on the power of your device.

Monte Carlo simulation in business


Monte Carlo simulation in business

Monte Carlo simulation is a mathematical technique that provides accurate estimates when working with uncertainties. It uses randomness to obtain meaningful information and is effective for calculating business risks and predicting failures such as cost or scheduling overruns.

AnyLogic enables Monte Carlo simulation for highly complex systems. With multimethod modeling simulated systems can be complex, dynamic, and non-linear. The results from these simulation models can come from parallel processing and cloud computing and made available in a variety of ways, including via API and custom UI. Learn more...

AnyLogic Cloud API: Python


AnyLogic Cloud API: Python

Introducing the AnyLogic Cloud API and Python. In this blog, see how to use the AnyLogic Cloud API with Python and evaluate its capabilities with an example model.

Python’s popularity ranks just behind that of JavaScript as the world’s second most popular language on GitHub. It is a popular language for machine learning, data processing, and data presentation. For AnyLogic, the Pypeline connector library allows you to call Python from within a running AnyLogic simulation model — learn more in our Pypeline webinar video. In this blog we will focus on the AnyLogic Cloud API and Python.

AnyLogic 9 overview and roadmap


AnyLogic 9 overview and roadmap

Upcoming features and functionality for AnyLogic 9 were previewed alongside AnyLogic 8.7 and AnyLogic Cloud developments at the online AnyLogic User Experience with MaxRad Software.

AnyLogic 9 will be a major update and many new details were revealed during the session from The AnyLogic Company CEO, Andrei Borshchev, Principle Software Engineer, Nikolai Churkov, and Head of AnyLogic Cloud Development, Alexander Rakulenko.

Here is the presentation recording with a follow-up question and answer session.

AnyLogic Cloud API: New Possibilities


AnyLogic Cloud API: New Possibilities

Along with the release of AnyLogic 8.5, came the new features of AnyLogic Cloud API 8.5.0. Using the API, you can configure and remotely run simulation models in the cloud, as well as create user interfaces for them. You can find out about these and other features in our previous blog. In this post, the focus is on analyzing the new features and trying out the examples.

Follow the examples and find out how to use the AnyLogic Cloud API to remotely run experiments and create custom user interfaces.

JavaScript code snippets are provided so that you can reproduce the examples for yourself. Here's what you need to get started! Dive in!